aiqbench analysis
This research presents a discrete-time neural network architecture that guarantees incremental dissipativity by construction, addressing critical stability requirements for robotics control loops without relying on computationally expensive ODE solvers. By embedding Lyapunov-based analysis directly into the model's parameterization, the approach ensures robustness in feedback systems while maintaining competitive prediction accuracy compared to baseline methods.
Learning Dissipative Dynamics with Dissipativity-by-Construction Discrete-Time Neural Networks
arXiv:2609.27188v1 Announce Type: new Abstract: Dissipativity is a fundamental system-theoretic property closely related to stability, passivity, and input--output stability, and is particularly important in robotics, where learned dynamics models are often embedded within feedback control loops. However, most existing approaches for learning dissipative dynamics are based on continuous-time formulations, which require ODE solvers during training or inference and can therefore be computationally expensive. Moreover, because practical implementations are inherently discrete-time, direct discretization of a continuous-time passive system does not necessarily preserve passivity, motivating the need for explicit discrete-time guarantees. This study proposes a method for learning incrementally dissipative dynamics from input--output time-series data using a deep multilayer perceptron formulated directly in discrete time. Through a constrained parameterization and a dedicated training procedure, the proposed model guarantees incremental dissipativity by construction rather than through regularization. Lyapunov-based analysis establishes the corresponding dissipativity and stability guarantees, while simulations on robotic dynamical systems demonstrate competitive prediction accuracy, computational efficiency, and consistent preservation of incremental dissipativity compared with baseline methods.
Abstract:Dissipativity is a fundamental system-theoretic property closely related to stability, passivity, and input--output stability, and is particularly important in robotics, where learned dynamics models are often embedded within feedback control loops. However, most existing approaches for learning dissipative dynamics are based on continuous-time formulations, which require ODE solvers during training or inference and can therefore be computationally expensive. Moreover, because practical implementations are inherently discrete-time, direct discretization of a continuous-time passive system does not necessarily preserve passivity, motivating the need for explicit discrete-time guarantees. This study proposes a method for learning incrementally dissipative dynamics from input--output time-series data using a deep multilayer perceptron formulated directly in discrete time. Through a constrained parameterization and a dedicated training procedure, the proposed model guarantees incremental dissipativity by construction rather than through regularization. Lyapunov-based analysis establishes the corresponding dissipativity and stability guarantees, while simulations on robotic dynamical systems demonstrate competitive prediction accuracy, computational efficiency, and consistent preservation of incremental dissipativity compared with baseline methods.
Robotics (cs.RO)
arXiv:2609.27188 [cs.RO]
(or arXiv:2609.27188v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.27188 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.13140/RG.2.2.19947.91682 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 263 words
Related coverage
Data-driven discrete-time deep recurrent neural network-based modeling for dissipative systems
arXiv · Sep 24, 2026
Port-Hamiltonian Koopman Operator Synthesis for Mechanical Systems
arXiv · Sep 16, 2026
University of Bristol Team Develops Stochastic Tsetlin Machine for Interpretable Learning
Quantum Zeitgeist · Jul 15, 2026
A unifying framework for quantum algorithms for time-dependent non-unitary dynamics
arXiv · Sep 22, 2026